Determining geographic locations for place names in a fact repository

• US 8,347,202 B1
• Filed: 03/14/2007
• Issued: 01/01/2013
• Est. Priority Date: 03/14/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Vespe, David, Hogue, Andrew
• Primary Examiner(s): NGUYEN, CHAU T
• Application Number:
  US11/686,217
• Time in Patent Office: 2,120 Days
• Field of Search: 715205-208, 715/211, 715/234, 715/760, 715/200
• US Class Current: 715/200
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/295 Named entity recognition

Abstract

A system and method for tagging place names with geographic location coordinates, the place names associated with a collection of objects in a memory of a computer system. The system and method process a text string within an object stored in memory to identify a first potential place name. The system and method determine whether geographic location coordinates are known for the first potential place name. The system and method identify the first potential place name associated with an object in the memory as a place name. The system and method tag the first identified place name associated with an object in the memory with its geographic location coordinates, when the geographic location coordinates for the first identified place name are known. The system and method disambiguate place names when multiple place names are found.

Claims

1. A computer-implemented method for tagging place names with geographic location coordinates, the method comprising:

at a server system having one or more processors and memory storing programs executed by the one or more processors to perform the method;

retrieving a first fact from a fact repository, the first fact having an attribute and a value, wherein the first fact is associated with a first object, the fact repository includes a plurality of objects and a plurality of facts associated with the plurality of objects, a respective fact in the fact repository includes a respective attribute and a respective value, the respective attribute is a text string, and the attribute of the first fact and plurality of values are extracted from free text in a plurality of web documents;

determining that the attribute of the first fact indicates that the value of the first fact is a potential place name; and

in response to the determining;

identifying a first potential place name corresponding to the value of the first fact;

determining geographic location coordinates for the first potential place name, including examining frequency with which the geographic location coordinates are associated with variations of the first potential place name; and

storing the determined geographic location coordinates in the fact repository, the storing including associating the determined geographic location coordinates with the first fact.

2. The method of claim 1, wherein the identifying a first potential place name comprises examining sequences of one or more capitalized words.

3. The method of claim 1, wherein the identifying a first potential place name comprises identifying a second potential place name in the value and examining words surrounding the second potential place name.

4. The method of claim 1, wherein the identifying a first potential place name comprises identifying various representations of a same place name.

5. The method of claim 1, wherein the attribute has been determined to correspond to a place name by comparing facts containing the same attribute.

6. The method of claim 1, wherein the identifying a first potential place name comprises comparing the first potential place name with an object name associated with an identified place name in the fact repository.

7. The method of claim 1, wherein the identifying a first potential place name comprises comparing the first potential place name with an identified place name associated with a second object in the fact repository.

8. The method of claim 1, wherein the determining geographic location coordinates for the first potential place name comprises examining a plurality of place names, wherein each of the plurality of place names has been tagged previously with its respective geographic location coordinates.

9. The method of claim 1, further comprising:

identifying a second potential place name in the value;

determining geographic location coordinates for the second potential place name;

identifying the second potential place name associated with an object in the fact repository as a second place name; and

tagging the second identified place name associated with an object in memory with its geographic location coordinates.

10. The method of claim 1, wherein the identifying a first potential place name further comprises:

storing in memory a rule that if a type of the object is a place, and if an attribute for a text string associated with the object is “

name”

, then the text string contains a place name; and

applying the rule to the first fact.

11. The method of claim 1, wherein the geographic location coordinates for the first potential place name comprise the geographic location coordinates for a bounding area surrounding the first potential place name, the bounding area having a shape selected from the group consisting of:

a circle, a triangle, a rectangle, a polygon, a line, and a point.

12. The method of claim 1, wherein the determining geographic location coordinates for the first potential place name comprises:

comparing potential geographic location coordinates for the first potential place name with the geographic location coordinates for an identified place name within the same object; and

retaining the potential geographic location coordinates for the first potential place name that have overlapping bounding areas with the geographic location coordinates for the identified place name, wherein each of the overlapping bounding areas has a shape selected from the group consisting of;

a circle, a triangle, a rectangle, a polygon, a line, and a point.

13. The method of claim 1, wherein the determining geographic location coordinates for the first potential place name comprises comparing potential geographic location coordinates for the first potential place name with the geographic location coordinates for an identified place name from a same source document as the source document containing the first potential place name.

14. A computer system for tagging place names with geographic location coordinates, the computer system comprising:

one or more processors;

memory;

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for;

retrieving a first fact from a fact repository, the first fact having an attribute and a value, wherein the first fact is associated with a first object, the fact repository includes a plurality of objects and a plurality of facts associated with the plurality of objects, a respective fact in the fact repository includes a respective attribute and a respective value, the respective attribute is a text string, and the attribute of the first fact and plurality of values are extracted from free text in a plurality of web documents;

determining that the attribute of the first fact indicates that the value of the first fact is a potential place name; and

in response to the determining;

identifying a first potential place name corresponding to the value of the first fact;

determining geographic location coordinates for the first potential place name, including examining frequency with which the geographic location coordinates are associated with variations of the first potential place name; and

storing the determined geographic location coordinates in the fact repository, the storing including associating the determined geographic location coordinates with the first fact.

15. A non-transitory computer-readable medium storing one or more programs, the one or more programs comprising instructions, which, when executed by a server system, cause the server system to perform a method comprising:

retrieving a first fact from a fact repository, the first fact having an attribute and a value, wherein the first fact is associated with a first object, the fact repository includes a plurality of objects and a plurality of facts associated with the plurality of objects, a respective fact in the fact repository includes a respective attribute and a respective value, the respective attribute is a text string, and the attribute of the first fact and plurality of values are extracted from free text in a plurality of web documents;

determining that the attribute of the first fact indicates that the value of the first fact is a potential place name; and

in response to the determining;

identifying a first potential place name corresponding to the value of the first fact;

determining geographic location coordinates for the first potential place name, including examining frequency with which the geographic location coordinates are associated with variations of the first potential place name;

storing the determined geographic location coordinates in the fact repository, the storing including associating the determined the geographic location coordinates with the first fact.

16. The non-transitory computer-readable medium of claim 15, wherein identifying a first potential place name comprises comparing an attribute name associated with the text string with an object name associated with an identified place name in the fact repository.

17. The non-transitory computer-readable medium of claim 15, wherein identifying a first potential place name comprises comparing the first potential place name with an identified place name associated with a second object in the fact repository.

18. A computer-implemented method for tagging place names with geographic location coordinates, the method comprising:

at a server system having one or more processors and memory storing programs executed by the one or more processors to perform the method;

retrieving a first fact from a fact repository, the first fact having an attribute and a value, wherein the first fact is associated with a first object, the fact repository includes a plurality of objects and a plurality of facts associated with the plurality of objects, a respective fact in the fact repository includes a respective attribute and a respective value, the respective attribute is a text string, and the attribute of the first fact and plurality of values are extracted from free text in a plurality of web documents;

determining that the attribute of the first fact indicates that the value of the first fact is a potential place name; and

in response to the determining;

identifying a first potential place name corresponding to the value of the first fact;

determining geographic location coordinates for the first potential place name, wherein the geographic location coordinates for the first potential place name comprise the geographic location coordinates for a bounding area surrounding the first potential place name, the bounding area having a shape selected from the group consisting of;

a circle, a triangle, a rectangle, a polygon, a line, and a point; and

storing the determined geographic location coordinates in the fact repository, the storing including associating the determined geographic location coordinates with the first fact.

19. A computer-implemented method for tagging place names with geographic location coordinates, the method comprising:

at a server system having one or more processors and memory storing programs executed by the one or more processors to perform the method;

retrieving a first fact from a fact repository, the first fact having an attribute and a value, wherein the first fact is associated with a first object, the fact repository includes a plurality of objects and a plurality of facts associated with the plurality of objects, a respective fact in the fact repository includes a respective attribute and a respective value, the respective attribute is a text string, and the attribute of the first fact and plurality of values are extracted from free text in a plurality of web documents;

determining that the attribute of the first fact indicates that the value of the first fact is a potential place name; and

in response to the determining;

identifying a first potential place name corresponding to the value of the first fact;

determining geographic location coordinates for the first potential place name, including;

comparing potential geographic location coordinates for the first potential place name with the geographic location coordinates for an identified place name within the same object; and

retaining the potential geographic location coordinates for the first potential place name that have overlapping bounding areas with the geographic location coordinates for the identified place name, wherein each of the overlapping bounding areas has a shape selected from the group consisting of;

a circle, a triangle, a rectangle, a polygon, a line, and a point; and

storing the determined geographic location coordinates in the fact repository, the storing including associating the determined geographic location coordinates with the first fact.